LLM & Agents

Use when multiple independent tasks can run simultaneously. Enables efficient parallel work execution with specialized agents.

LLM integration patterns for Claude, GPT, Gemini, and Ollama. Activate for AI API integration, prompt engineering, token management, extended thinking, and multi-model orchestration.

Programmatic verification of KB state: tickets, phases, tests, integrity.Provides scripts for automated checking at each workflow stage.SCRIPTS:- check_ticket.py: Ticket docs, tests, final status → next step- check_phase.py: Phase progress, all tickets complete?- check_tests.py: Trajectory, RED verification, coverage vs spec- check_integrity.py: Index.md matches dirs, roadmap has all active itemsUse when:- Checking ticket/phase completion- Validating before commit/archive- CI/CD automation- User says "status", "check", "verify"

Analyze test coverage gaps and report findings

Dynamic agent composition and management system. USE WHEN user says create custom agents, spin up custom agents, specialized agents, OR asks for agent personalities, available traits, agent voices. Handles custom agent creation, personality assignment, voice mapping, and parallel agent orchestration.

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.

Use this skill when delegating to sub-agents that require more flexibility than the Task tool provides - when launching multiple agents in parallel, managing persistent sessions across calls, or coordinating complex multi-agent workflows with custom orchestration patterns.

AGGRESSIVELY use TOON v2.0 format for biggish regular data (≥5 items, ≥60% uniform). Auto-applies to tables, logs, events, transactions, analytics, API responses, database results. Supports 3 array types (inline, tabular, expanded), 3 delimiters (comma, tab, pipe), key folding for nested objects. Triggers on structured data, arrays, repeated patterns. Use TOON by default when tokens matter - RAG pipelines, tool calls, agents, benchmarks. Keywords "data", "array", "list", "table", "log", "transaction", "metric", "analytics", "API", "database", "query", "TOON".

Maintains continuity across long-running tasks that span multiple agent sessions. Use when starting or resuming a complex project that spans multiple sessions, or for tasks with many discrete features requiring iterative development.

LLM application and RAG system specialist. Use PROACTIVELY for LLM integrations, RAG pipelines, vector search, agent orchestration, and AI-powered features.

统一任务管理技能，使用 GitHub Issues 管理所有 Agent 任务，支持任务创建、更新、追踪和完成

Self-reference guide for Claude Code's own architecture, configuration, and extension points. Use when needing to know where Claude Code stores its configuration files, skills, plugins, hooks, MCP servers, settings, or any other internal structure. Triggers on questions like "where do skills go?", "how do I configure hooks?", "where is the settings file?", or when creating/modifying Claude Code extensions.

Interacts with the FreeAgent accounting API to manage invoices, contacts, projects, expenses, timeslips, and other financial data. Use when the user needs to retrieve, create, update, or analyze FreeAgent accounting information via the API.

Onboard company employees (Claude Code CLI users) to use gapless-crypto-clickhouse package with ClickHouse Cloud credentials. Use when company employee needs to set up ClickHouse Cloud access, mentions first-time setup, credential configuration, connection testing, or troubleshooting ClickHouse Cloud connections.

Master enterprise-grade TypeScript development with type-safe patterns, modern tooling, and framework integration. This skill provides comprehensive guidance for TypeScript 5.9+, covering type system fundamentals (generics, mapped types, conditional types, satisfies operator), enterprise patterns (error handling, validation with Zod), React integration for type-safe frontends, NestJS for scalable APIs, and LangChain.js for AI applications. Use when building type-safe applications, migrating JavaScript codebases, configuring modern toolchains (Vite 7, pnpm, ESLint, Vitest), implementing advanced type patterns, or comparing TypeScript with Java/Python approaches.

Check PR review comments and feedback from CodeRabbit and human reviewers. Use when user asks about reviews, unresolved comments, CodeRabbit feedback, Claude review, or PR status.

Multi-agent code analysis orchestration using claudemem. Share claudemem output across parallel agents. Enables parallel investigation, consensus analysis, and role-based command mapping.

Connect to Beam AI workspace for agent management. Load when user mentions 'beam', 'beam agent', 'beam task', 'beam analytics', 'list agents', 'create task', or any Beam AI operations. Meta-skill that validates config, discovers agents, and routes to appropriate operations.

Use OpenAI Codex CLI to answer questions about code, analyze files, or perform read-only codebase exploration. Invoke this skill when the user asks to use Codex, wants a second opinion from another AI agent, or wants to compare Claude's answer with Codex's response.

Use when analyzing existing codebases to generate architecture documentation - coordinates subagent-driven exploration with mandatory workspace structure, validation gates, and pressure-resistant workflows